Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Changes in the system prompt between Claude Opus 4.6 and 4.7

simonwillison.net

Post reply on HN
Print view View original

91–100 of 240 posts

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#91

Post by zozbot234 »

layer8 wrote: post #87
zozbot234 wrote: post #79

Earlier quoted context omitted.

That part of the system prompt is just stating that telling someone who has an actual eating disorder to start counting calories or micro-manage their eating in other ways (a suggestion that the model might well give to an average person for the sake of clear argument, which would then be understood sensibly and taken with a grain of salt) is likely to make them worse off, not better off. This seems like a common-sen…

If it’s common sense, shouldn’t the model know it already?

Shouldn't the model "know" that if I have to wash my car at the carwash, I can't just go there on foot? It's not that simple!

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#92

Post by adw »

naasking wrote: post #30
embedding-shape wrote: post #6

> The new section includes: When a request leaves minor details unspecified, the person typically wants Claude to make a reasonable attempt now, not to be interviewed first. Uff, I've tried stuff like these in my prompts, and the results are never good, I much prefer the agent to prompt me upfront to resolve that before it "attempts" whatever it wants, kind of surprised to see that they added that

Seriously, when you're conversing with a person would you prefer they start rambling on their own interpretation or would you prefer they ask you to clarify? The latter seems pretty natural and obvious. Edit: That said, it's entirely possible that large and sophisticated LLMs can invent some pretty bizarre but technically possible interpretations, so maybe this is to curb that tendency.

When you’re staffing work to a junior, though, often it’s the opposite.

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#93

Post by arcanemachiner »

goosejuice wrote: post #69
WarmWash wrote: post #41

Earlier quoted context omitted.

When you are worth hundreds of billions, people start falling over themselves running to file lawsuits against you. We're already seeing this happen. So spending $50M to fund a team to weed out "food for crazies" becomes a no-brainer.

It is a no brainer. If a company of any size is putting out a product that caused cancer we wouldn't think twice about suing them. Why should mental health disorders be any different?

Why stop there? We could jam up the system prompt with all kinds of irrelevant guardrails to prevent harm to groups X, Y, and Z!

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#94

Post by PunchyHamster »

embedding-shape wrote: post #6

> The new section includes: When a request leaves minor details unspecified, the person typically wants Claude to make a reasonable attempt now, not to be interviewed first. Uff, I've tried stuff like these in my prompts, and the results are never good, I much prefer the agent to prompt me upfront to resolve that before it "attempts" whatever it wants, kind of surprised to see that they added that

well, clarifying means burning more tokens...

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#96

Post by KolenCh »

mwexler wrote: post #45

Interesting that it's not a direct "you should" but an omniscient 3rd person perspective "Claude should". Also full of "can" and "should" phrases: feels both passive and subjunctive as wishes, vs strict commands (I guess these are better termed “modals”, but not an expert)

“Claude” is more specific than “you”. Why rely on attention to figure out who’s the subject? Also it is in their (people from Anthropic) believe that rule based alignment won’t work and that’s why they wrote the soul document as “something like you’d write to your child to show them how they should behave in the world” (I paraphrase). I guess system prompt should be similar in this aspect.

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#97

Post by jwpapi »

ikari_pl wrote: post #85

> Claude keeps its responses focused and concise so as to avoid potentially overwhelming the user with overly-long responses. Even if an answer has disclaimers or caveats, Claude discloses them briefly and keeps the majority of its response focused on its main answer. I am strongly opinionated against this. I use Claude in some low-level projects where these answers are saving me from making really silly things, as w…

agree!

For low level I recommend to run tests as early as you can and verify whatever information you got when you learn, build a fundamental understanding

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#98

Post by PunchyHamster »

adw wrote: post #92
naasking wrote: post #30

Earlier quoted context omitted.

Seriously, when you're conversing with a person would you prefer they start rambling on their own interpretation or would you prefer they ask you to clarify? The latter seems pretty natural and obvious. Edit: That said, it's entirely possible that large and sophisticated LLMs can invent some pretty bizarre but technically possible interpretations, so maybe this is to curb that tendency.

When you’re staffing work to a junior, though, often it’s the opposite.

So you are saying they are trying for the whole Artificial Intern vibe ?

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#100

Post by lishuaiJing03 »

ikari_pl wrote: post #82
embedding-shape wrote: post #6

> The new section includes: When a request leaves minor details unspecified, the person typically wants Claude to make a reasonable attempt now, not to be interviewed first. Uff, I've tried stuff like these in my prompts, and the results are never good, I much prefer the agent to prompt me upfront to resolve that before it "attempts" whatever it wants, kind of surprised to see that they added that

I usually need to remind it 5 times to do the opposite - because it makes decisions that I don't like or that are harmful to the project—so if it lands in Claude Code too, I have hard times ahead. I try to explicitly request Claude to ask me follow-up questions, especially multiple-choice ones (it explains possible paths nicely), but if I don't, or when it decides to ignore the instructions (which happens a lot), the…

it is a big problem that many I know face every day. sometimes we are just wondering are we the dumb ones since the demo shows everything just works.
Post reply on HN